© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128688
    Prev
    Next
    INDEX
    Explanations

    terms related to landscape architecture and design processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentView
    -0.07
     Loft
    -0.07
    reff
    -0.07
     तह
    -0.07
     karak
    -0.07
    質
    -0.07
     طبÙĤÙĩ
    -0.07
     kalp
    -0.07
    umbnails
    -0.07
    bast
    -0.07
    POSITIVE LOGITS
     garden
    0.08
     yard
    0.08
     landsc
    0.07
     beaut
    0.07
     scar
    0.07
     manic
    0.07
     dise
    0.07
     sculpt
    0.07
     lawn
    0.07
     driv
    0.07
    Activations Density 0.027%

    No Known Activations